mlsanityData to 7 Oct 2026

Adversarial Robustness with Non-uniform Perturbations

arXiv 2102.12002 ↗First posted 24 Feb 2021cs.LG cs.AI cs.CRcited by 17

Not on the map. Why?

Abstract (arXiv)

Robustness of machine learning models is critical for security related applications, where real-world adversaries are uniquely focused on evading neural network based detectors. Prior work mainly focus on crafting adversarial examples (AEs) with small uniform norm-bounded perturbations across features to maintain the requirement of imperceptibility. However, uniform perturbations do not result in realistic AEs in domains such as malware, finance, and social networks. For these types of applications, features typically have some semantically meaningful dependencies. The key idea of our proposed approach is to enable non-uniform perturbations that can adequately represent these feature dependencies during adversarial training. We propose using characteristics of the empirical data distribution, both on correlations between the features and the importance of the features themselves. Using experimental datasets for malware classification, credit risk prediction, and spam detection, we show that our approach is more robust to real-world attacks. Finally, we present robustness certification utilizing non-uniform perturbation bounds, and show that non-uniform bounds achieve better certification.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 23 of its 49 references that are in the map. First posted on arXiv 24 Feb 2021.

Builds on

23 of 49 references.

References · 23

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  6. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  7. 2016Adversarial Machine Learning at Scalecited by 934
  8. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  9. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  10. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  11. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  12. 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 178
11 more
  1. 2018EMBER: An Open Dataset for Training Static PE Malware Machine Learning Modelscited by 164
  2. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  3. 2018TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Timecited by 108
  4. 2020Learning perturbation sets for robust machine learningcited by 48
  5. 2020Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Freecited by 48
  6. 2019Imperceptible Adversarial Attacks on Tabular Datacited by 35
  7. 2020Adversarial Deep Ensemble: Evasion Attacks and Defenses for Malware Detectioncited by 33
  8. 2017Improving Robustness of ML Classifiers against Realizable Evasion Attacks Using Conserved Featurescited by 18
  9. 2020Generating End-to-End Adversarial Examples for Malware Classifiers Using Explainabilitycited by 9
  10. 2020Not All Datasets Are Born Equal: On Heterogeneous Data and Adversarial Examplescited by 9
  11. 2019On Certifying Non-uniform Bound against Adversarial Attackscited by 6

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 5; 2023: 1; 2024: 6; 2025: 3.

17 papers.

Sort:

By area:

  1. 2021A Unified Framework for Adversarial Attack and Defense in Constrained Feature Spacecited by 22
  2. 2023Projected Randomized Smoothing for Certified Adversarial Robustnesscited by 11
  3. 2021Feature Importance Guided Attack: A Model Agnostic Adversarial Attackcited by 10
  4. 2024Verification of Neural Networks' Global Robustnesscited by 10
  5. 2024Investigating Imperceptibility of Adversarial Attacks on Tabular Data: An Empirical Analysiscited by 4
  6. 2025TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Datacited by 4
  7. 2024Living off the Analyst: Harvesting Features from Yara Rules for Malware Detectioncited by 3
  8. 2022Adversarial Attack and Defense for Non-Parametric Two-Sample Testscited by 2
  9. 2022Level Up with ML Vulnerability Identification: Leveraging Domain Constraints in Feature Space for Robust Android Malware Detectioncited by 2
  10. 2022An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Modelscited by 1
  11. 2022Towards Generating Adversarial Examples on Mixed-type Datacited by 1
  12. 2024Towards Independence Criterion in Machine Unlearning of Features and Labelscited by 1
5 more
  1. 2022Firenze: Model Evaluation Using Weak Signalscited by 0
  2. 2024Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothingcited by 0
  3. 2024Bypassing DARCY Defense: Indistinguishable Universal Adversarial Triggerscited by 0
  4. 2025Disentangling Safe and Unsafe Corruptions via Anisotropy and Localitycited by 0
  5. 2025Insights on Adversarial Attacks for Tabular Machine Learning via a Systematic Literature Reviewcited by 0